Dynamic Neural Network Based Very Short-Term Wind Speed Forecasting

In this paper, the nonlinear autoregressive model with exogenous inputs (NARX) is proposed for wind speed forecast. Forecasting wind speed is a challenging task in wind energy research domain which influences the dynamic control of wind turbine and for system scheduling. The aim of this study is to obtain suitable forecast model for wind speed with time series input variables such as wind direction, humidity, pressure and time. The meteorological data observed with 15 minute time intervals is used for the model and the performance is evaluated and compared with the back propagation neural network (BPNN). The result shows that the proposed model outperforms the BPNN based on the metrics used.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[2]  Arash Andalib,et al.  Forecasting the Unknown Dynamics in NN3 Database Using a Nonlinear Autoregressive Recurrent Neural Network , 2007, 2007 International Joint Conference on Neural Networks.

[3]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[4]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[5]  Hong-Te Su,et al.  Identification of Chemical Processes using Recurrent Networks , 1991, 1991 American Control Conference.

[6]  Chao Chen,et al.  A hybrid statistical method to predict wind speed and wind power , 2010 .

[7]  P. Werbos,et al.  Long-term predictions of chemical processes using recurrent neural networks: a parallel training approach , 1992 .

[8]  Ramesh Babu,et al.  Forecasting of Wind Speed Using Artificial Neural Networks , 2014 .

[9]  Shuhui Li,et al.  Using neural networks to estimate wind turbine power generation , 2001 .

[10]  Hang Xie,et al.  Time series prediction based on NARX neural networks: An advanced approach , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[11]  Farshid Keynia,et al.  A new hybrid iterative method for short‐term wind speed forecasting , 2011 .

[12]  Ramesh Babu,et al.  Improving Forecast Accuracy of Wind Speed Using Wavelet Transform and Neural Networks , 2013 .

[13]  Zhang Yan,et al.  A review on the forecasting of wind speed and generated power , 2009 .

[14]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[15]  N. RAMESH BABU,et al.  WIND ENERGY CONVERSION SYSTEMS-A TECHNICAL REVIEW , 2013 .

[16]  Fugen Song,et al.  Sunspot Forecasting by Using Chaotic Time-series Analysis and NARX Network , 2011, J. Comput..

[17]  E. El-Saadany,et al.  Grey Predictors for Hourly Wind Speed and Power Forecasting , 2012 .

[18]  Eugene Fernandez,et al.  Analysis of wind power generation and prediction using ANN: A case study , 2008 .

[19]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[20]  Min-Seok Kim,et al.  Short-term electric load forecasting using data mining technique , 2013 .